# StyleDecoupler: Generalizable Artistic Style Disentanglement

arXiv: https://arxiv.org/abs/2601.17697 · HTML: https://mlsanity.com/paper/2601.17697/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 24 references that are in the map.
- First posted on arXiv 25 Jan 2026.

## Builds on (most cited first, 17 of 17)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs](https://mlsanity.com/paper/2311.13600/) (2023)
- [Measuring Style Similarity in Diffusion Models](https://mlsanity.com/paper/2404.01292/) (2024)
- [Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/1912.01230/) (2019)
- [ArtFID: Quantitative Evaluation of Neural Style Transfer](https://mlsanity.com/paper/2207.12280/) (2022)
- [Evaluating Data Attribution for Text-to-Image Models](https://mlsanity.com/paper/2306.09345/) (2023)
- [ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity](https://mlsanity.com/paper/2103.09776/) (2021)
- [GalleryGPT: Analyzing Paintings with Large Multimodal Models](https://mlsanity.com/paper/2408.00491/) (2024)
- [Semantic to Structure: Learning Structural Representations for Infringement Detection](https://mlsanity.com/paper/2502.07323/) (2025)
- [AI Art Neural Constellation: Revealing the Collective and Contrastive State of AI-Generated and Human Art](https://mlsanity.com/paper/2402.02453/) (2024)
- [A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets](https://mlsanity.com/paper/2507.04699/) (2025)
- [Control-CLIP: Decoupling Category and Style Guidance in CLIP for Specific-Domain Generation](https://mlsanity.com/paper/2502.11532/) (2025)
- [From Imitation to Innovation: The Emergence of AI Unique Artistic Styles and the Challenge of Copyright Protection](https://mlsanity.com/paper/2507.04769/) (2025)

## Built on by (most cited first, 3 of 3)

- [Evaluating Generative Models via One-Dimensional Code Distributions](https://mlsanity.com/paper/2603.08064/) (2026)
- [CoDA: Color Distribution Probing for Efficient and Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2605.24306/) (2026)
- [Chameleon: Style-Content Disentangled Framework for Cross-Domain Object Compositing](https://mlsanity.com/paper/2606.01079/) (2026)

## Abstract (arXiv)

Representing artistic style is challenging due to its deep entanglement with semantic content. We propose StyleDecoupler, an information-theoretic framework that leverages a key insight: multi-modal vision models encode both style and content, while uni-modal models suppress style to focus on content-invariant features. By using uni-modal representations as content-only references, we isolate pure style features from multi-modal embeddings through mutual information minimization. StyleDecoupler operates as a plug-and-play module on frozen Vision-Language Models without fine-tuning. We also introduce WeART, a large-scale benchmark of 280K artworks across 152 styles and 1,556 artists. Experiments show state-of-the-art performance on style retrieval across WeART and WikiART, while enabling applications like style relationship mapping and generative model evaluation. We release our method and dataset at this url.